From: Michael Zuckerman <Michael.zuckerman@intel.com>
Date: Wed, 25 May 2016 14:04:21 +0000 (+0000)
Subject: [Clang][AVX512][BUILTIN] Add missing intrinsics for cast
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=1c3b22987674a09aeb2d7dcc65cfc2d2d722e39b;p=clang

[Clang][AVX512][BUILTIN] Add missing intrinsics for cast

Differential Revision: http://reviews.llvm.org/D20523



git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@270699 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Headers/avx512fintrin.h b/lib/Headers/avx512fintrin.h
index 57a1de00b2..297c9b873d 100644
--- a/lib/Headers/avx512fintrin.h
+++ b/lib/Headers/avx512fintrin.h
@@ -337,12 +337,35 @@ _mm512_castpd512_pd128(__m512d __a)
   return __builtin_shufflevector(__a, __a, 0, 1);
 }
 
+static __inline __m256d __DEFAULT_FN_ATTRS
+_mm512_castpd512_pd256 (__m512d __A)
+{
+  return __builtin_shufflevector(__A, __A, 0, 1, 2, 3);
+}
+
 static __inline __m128 __DEFAULT_FN_ATTRS
 _mm512_castps512_ps128(__m512 __a)
 {
   return __builtin_shufflevector(__a, __a, 0, 1, 2, 3);
 }
 
+static __inline __m256 __DEFAULT_FN_ATTRS
+_mm512_castps512_ps256 (__m512 __A)
+{
+  return __builtin_shufflevector(__A, __A, 0, 1, 2, 3, 4, 5, 6, 7);
+}
+
+static __inline __m512 __DEFAULT_FN_ATTRS
+_mm512_castpd_ps (__m512d __A)
+{
+  return (__m512) (__A);
+}
+
+static __inline __m512i __DEFAULT_FN_ATTRS
+_mm512_castpd_si512 (__m512d __A)
+{
+  return (__m512i) (__A);
+}
 
 static __inline__ __m512d __DEFAULT_FN_ATTRS
 _mm512_castpd128_pd512 (__m128d __A)
@@ -350,6 +373,18 @@ _mm512_castpd128_pd512 (__m128d __A)
   return __builtin_shufflevector( __A, __A, 0, 1, -1, -1, -1, -1, -1, -1);
 }
 
+static __inline __m512d __DEFAULT_FN_ATTRS
+_mm512_castps_pd (__m512 __A)
+{
+  return (__m512d) (__A);
+}
+
+static __inline __m512i __DEFAULT_FN_ATTRS
+_mm512_castps_si512 (__m512 __A)
+{
+  return (__m512i) (__A);
+}
+
 static __inline__ __m512 __DEFAULT_FN_ATTRS
 _mm512_castps128_ps512 (__m128 __A)
 {
@@ -368,6 +403,24 @@ _mm512_castsi256_si512 (__m256i __A)
    return  __builtin_shufflevector( __A, __A, 0, 1, 2, 3, -1, -1, -1, -1);
 }
 
+static __inline __m512 __DEFAULT_FN_ATTRS
+_mm512_castsi512_ps (__m512i __A)
+{
+  return (__m512) (__A);
+}
+
+static __inline __m512d __DEFAULT_FN_ATTRS
+_mm512_castsi512_pd (__m512i __A)
+{
+  return (__m512d) (__A);
+}
+
+static __inline __m128i __DEFAULT_FN_ATTRS
+_mm512_castsi512_si128 (__m512i __A)
+{
+  return (__m128i)__builtin_shufflevector(__A, __A , 0, 1);
+}
+
 /* Bitwise operators */
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_and_epi32(__m512i __a, __m512i __b)
diff --git a/test/CodeGen/avx512f-builtins.c b/test/CodeGen/avx512f-builtins.c
index b98be5ff03..2100507715 100644
--- a/test/CodeGen/avx512f-builtins.c
+++ b/test/CodeGen/avx512f-builtins.c
@@ -328,13 +328,6 @@ __m512d test_mm512_set1_pd(double d)
   return _mm512_set1_pd(d);
 }
 
-__m512d test_mm512_castpd256_pd512(__m256d a)
-{
-  // CHECK-LABEL: @test_mm512_castpd256_pd512
-  // CHECK: shufflevector <4 x double> {{.*}} <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
-  return _mm512_castpd256_pd512(a);
-}
-
 __mmask16 test_mm512_knot(__mmask16 a)
 {
   // CHECK-LABEL: @test_mm512_knot
@@ -5925,10 +5918,25 @@ __m256i test_mm512_maskz_cvttpd_epu32(__mmask8 __U, __m512d __A) {
   return _mm512_maskz_cvttpd_epu32(__U, __A); 
 }
 
-__m512d test_mm512_castpd128_pd512(__m128d __A) {
-  // CHECK-LABEL: @test_mm512_castpd128_pd512
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-  return _mm512_castpd128_pd512(__A); 
+__m512 test_mm512_castpd_ps (__m512d __A)
+{
+  // CHECK-LABEL: @test_mm512_castpd_ps 
+  // CHECK: bitcast <8 x double> %1 to <16 x float>
+  return _mm512_castpd_ps (__A);
+}
+
+__m512d test_mm512_castps_pd (__m512 __A)
+{
+  // CHECK-LABEL: @test_mm512_castps_pd 
+  // CHECK: bitcast <16 x float> %1 to <8 x double>
+  return _mm512_castps_pd (__A);
+}
+
+__m512i test_mm512_castpd_si512 (__m512d __A)
+{
+  // CHECK-LABEL: @test_mm512_castpd_si512 
+  // CHECK: bitcast <8 x double> %1 to <8 x i64>
+  return _mm512_castpd_si512 (__A);
 }
 
 __m512 test_mm512_castps128_ps512(__m128 __A) {
@@ -5937,6 +5945,39 @@ __m512 test_mm512_castps128_ps512(__m128 __A) {
   return _mm512_castps128_ps512(__A); 
 }
 
+__m512d test_mm512_castpd128_pd512(__m128d __A) {
+  // CHECK-LABEL: @test_mm512_castpd128_pd512
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+  return _mm512_castpd128_pd512(__A); 
+}
+
+__m512d test_mm512_castpd256_pd512(__m256d a)
+{
+  // CHECK-LABEL: @test_mm512_castpd256_pd512
+  // CHECK: shufflevector <4 x double> {{.*}} <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+  return _mm512_castpd256_pd512(a);
+}
+
+__m256d test_mm512_castpd512_pd256 (__m512d __A)
+{
+  // CHECK-LABEL: @test_mm512_castpd512_pd256 
+  // CHECK: shufflevector <8 x double> %1, <8 x double> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  return _mm512_castpd512_pd256 (__A);
+}
+
+__m256 test_mm512_castps512_ps256 (__m512 __A)
+{
+  // CHECK-LABEL: @test_mm512_castps512_ps256 
+  // CHECK: shufflevector <16 x float> %1, <16 x float> %2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  return _mm512_castps512_ps256 (__A);
+}
+
+__m512i test_mm512_castps_si512 (__m512 __A)
+{
+  // CHECK-LABEL: @test_mm512_castps_si512 
+  // CHECK: bitcast <16 x float> %1 to <8 x i64>
+  return _mm512_castps_si512 (__A);
+}
 __m512i test_mm512_castsi128_si512(__m128i __A) {
   // CHECK-LABEL: @test_mm512_castsi128_si512
   // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
@@ -5949,6 +5990,26 @@ __m512i test_mm512_castsi256_si512(__m256i __A) {
   return _mm512_castsi256_si512(__A); 
 }
 
+__m512 test_mm512_castsi512_ps (__m512i __A)
+{
+  // CHECK-LABEL: @test_mm512_castsi512_ps 
+  // CHECK: bitcast <8 x i64> %1 to <16 x float>
+  return _mm512_castsi512_ps (__A);
+}
+
+__m512d test_mm512_castsi512_pd (__m512i __A)
+{
+  // CHECK-LABEL: @test_mm512_castsi512_pd 
+  // CHECK: bitcast <8 x i64> %1 to <8 x double>
+  return _mm512_castsi512_pd (__A);
+}
+
+__m128i test_mm512_castsi512_si128 (__m512i __A)
+{
+  // CHECK-LABEL: @test_mm512_castsi512_si128 
+  // CHECK: shufflevector <8 x i64> %1, <8 x i64> %2, <2 x i32> <i32 0, i32 1>
+  return _mm512_castsi512_si128 (__A);
+}
 
 __m128 test_mm_cvt_roundsd_ss(__m128 __A, __m128d __B) {
   // CHECK-LABEL: @test_mm_cvt_roundsd_ss